{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IUKL3MGT5ARIPVU5N5V7SM7GZD","short_pith_number":"pith:IUKL3MGT","schema_version":"1.0","canonical_sha256":"4514bdb0d3e82287d69d6f6bf933e6c8e9d3385d02397ad6faa7b206390b6266","source":{"kind":"arxiv","id":"2506.11166","version":1},"attestation_state":"computed","paper":{"title":"Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ji Young Byun, Navid Azizan, Rama Chellappa, Young-Jin Park","submitted_at":"2025-06-11T22:23:38Z","abstract_excerpt":"As a cornerstone of patient care, clinical decision-making significantly influences patient outcomes and can be enhanced by large language models (LLMs). Although LLMs have demonstrated remarkable performance, their application to visual question answering in medical imaging, particularly for reasoning-based diagnosis, remains largely unexplored. Furthermore, supervised fine-tuning for reasoning tasks is largely impractical due to limited data availability and high annotation costs. In this work, we introduce a zero-shot framework for reliable medical image diagnosis that enhances the reasonin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.11166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T22:23:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c29614ccf42b829cc88358e8fd185043a58989ae9661c9450a9eae1243a3050","abstract_canon_sha256":"324ab5e4b04aefdebee3909a5d81916331663f72c53522ebdad8ed7bdbcc7e25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:00.658725Z","signature_b64":"MMFyxz9JMiq3NwgtFWNMjwDUd4AiwfsvenZnCiv25MP8vPBlRDhNPTxlI1sYIfGUdOB8zgjANMovt+aSIfcfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4514bdb0d3e82287d69d6f6bf933e6c8e9d3385d02397ad6faa7b206390b6266","last_reissued_at":"2026-07-05T11:21:00.658219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:00.658219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ji Young Byun, Navid Azizan, Rama Chellappa, Young-Jin Park","submitted_at":"2025-06-11T22:23:38Z","abstract_excerpt":"As a cornerstone of patient care, clinical decision-making significantly influences patient outcomes and can be enhanced by large language models (LLMs). Although LLMs have demonstrated remarkable performance, their application to visual question answering in medical imaging, particularly for reasoning-based diagnosis, remains largely unexplored. Furthermore, supervised fine-tuning for reasoning tasks is largely impractical due to limited data availability and high annotation costs. In this work, we introduce a zero-shot framework for reliable medical image diagnosis that enhances the reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11166","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.11166/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.11166","created_at":"2026-07-05T11:21:00.658275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11166v1","created_at":"2026-07-05T11:21:00.658275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11166","created_at":"2026-07-05T11:21:00.658275+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUKL3MGT5ARI","created_at":"2026-07-05T11:21:00.658275+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUKL3MGT5ARIPVU5","created_at":"2026-07-05T11:21:00.658275+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUKL3MGT","created_at":"2026-07-05T11:21:00.658275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD","json":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD.json","graph_json":"https://pith.science/api/pith-number/IUKL3MGT5ARIPVU5N5V7SM7GZD/graph.json","events_json":"https://pith.science/api/pith-number/IUKL3MGT5ARIPVU5N5V7SM7GZD/events.json","paper":"https://pith.science/paper/IUKL3MGT"},"agent_actions":{"view_html":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD","download_json":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD.json","view_paper":"https://pith.science/paper/IUKL3MGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11166&json=true","fetch_graph":"https://pith.science/api/pith-number/IUKL3MGT5ARIPVU5N5V7SM7GZD/graph.json","fetch_events":"https://pith.science/api/pith-number/IUKL3MGT5ARIPVU5N5V7SM7GZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD/action/storage_attestation","attest_author":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD/action/author_attestation","sign_citation":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD/action/citation_signature","submit_replication":"https://pith.science/pith/IUKL3MGT5ARIPVU5N5V7SM7GZD/action/replication_record"}},"created_at":"2026-07-05T11:21:00.658275+00:00","updated_at":"2026-07-05T11:21:00.658275+00:00"}